Skip to content

1.3.0

Latest
Latest
Compare
Choose a tag to compare
@tennlee tennlee released this 15 Nov 00:30
1.3.0
a6ea2e7
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.

Release Notes (What's New)

Version 1.3.0 (November 15, 2024)

For a list of all changes in this release, see the full changelog. Below are the changes we think users may wish to be aware of.

Introduced Support for Python 3.13 and Dropped Support for Python 3.9

  • In line with other scientific Python packages, scores has dropped support for Python 3.9 in this release.
    scores has added support for Python 3.13. See PR #710.

Features

  • Added four new metrics:
    • Quantile Interval Score: scores.continuous.quantile_interval_score. See PR #704, PR #733 and PR #738.
    • Interval Score: scores.continuous.interval_score. See PR #704, PR #733 and PR #738.
    • Kling-Gupta Efficiency (KGE): scores.continuous.kge. See PR #679, PR #700 and PR #734.
    • Interval threshold weighted continuous ranked probability score (twCRPS) for ensembles: scores.probability.interval_tw_crps_for_ensemble. See PR #682 and PR #734.
  • Added an optional include_components argument to several continuous ranked probability score (CRPS) functions for ensembles. If supplied, the include_components argument will return the underforecast penalty, the overforecast penalty and the forecast spread term, in addition to the overall CRPS value. This applies to the following CRPS functions:
    • continuous ranked probability score (CRPS) for ensembles: scores.probability.crps_for_ensemble
    • threshold weighted continuous ranked probability score (twCRPS) for ensembles: scores.probability.tw_crps_for_ensemble
    • tail threshold weighted continuous ranked probability score (twCRPS) for ensembles: scores.probability.tail_tw_crps_for_ensemble
    • interval threshold weighted continuous ranked probability score (twCRPS) for ensembles: scores.probability.interval_tw_crps_for_ensemble)
      See PR #708 and PR #734.

Documentation

  • Added "Kling–Gupta Efficiency (KGE)" tutorial. See PR #679, PR #700 and PR #734.
  • Added "Quantile Interval Score and Interval Score" tutorial. See PR #704, PR #736 and PR #738.
  • Added "Threshold Weighted Continuous Ranked Probability Score (twCRPS) for ensembles" tutorial. See PR #706 and PR #722.
  • Updated the title in the "Binary Categorical Scores and Binary Contingency Tables (Confusion Matrices)" tutorial and the description for the corresponding thumbnail in the tutorial gallery. See PR #741 and PR #743.
  • Updated the pull request template. See PR #719.

Internal Changes

  • Sped up (improved the computational efficiency of) the continuous ranked probability score (CRPS) for ensembles. This also addresses memory issues when a large number of ensemble members are present. See PR #694.

Contributors to this Release

Mohammadreza Khanarmuei (@reza-armuei), Nicholas Loveday (@nicholasloveday), Durga Shrestha (@durgals), Tennessee Leeuwenburg (@tennlee), Stephanie Chong (@Steph-Chong) and Robert J. Taggart (@rob-taggart).

Assets 2
Loading